{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T08:13:44Z","timestamp":1774944824181,"version":"3.50.1"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","award":["RS-2021-II211341"],"award-info":[{"award-number":["RS-2021-II211341"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","award":["RS-2024-00352578"],"award-info":[{"award-number":["RS-2024-00352578"]}],"id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002460","name":"Chung-Ang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002460","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.cviu.2026.104661","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:49:51Z","timestamp":1768981791000},"page":"104661","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["3D-aware virtual try-on using only 2D inputs"],"prefix":"10.1016","volume":"264","author":[{"given":"Jaeyoon","family":"Lee","sequence":"first","affiliation":[]},{"given":"Hojoon","family":"Jung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9753-8760","authenticated-orcid":false,"given":"Jongwon","family":"Choi","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104661_b1","series-title":"Outfit anyone [online]","author":"Alibaba","year":"2023"},{"key":"10.1016\/j.cviu.2026.104661_b2","doi-asserted-by":"crossref","unstructured":"Black,\u00a0M.J., Patel,\u00a0P., Tesch,\u00a0J., Yang,\u00a0J., 2023. BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion. In: Conference on Computer Vision and Pattern Recognition. pp. 8726\u20138737.","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"10.1016\/j.cviu.2026.104661_b3","doi-asserted-by":"crossref","first-page":"3545","DOI":"10.1007\/s00371-023-02946-3","article-title":"Three stages of 3D virtual try-on network with appearance flow and shape field","author":"Chen","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104661_b4","doi-asserted-by":"crossref","unstructured":"Cho,\u00a0S., Hong,\u00a0S., Kim,\u00a0S., 2022. Cats++: Boosting cost aggregation with convolutions and transformers. In: IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2022.3218727"},{"key":"10.1016\/j.cviu.2026.104661_b5","doi-asserted-by":"crossref","unstructured":"Choi,\u00a0S., S.Park, Lee,\u00a0M., Choo,\u00a0J., 2021. Viton-hd: High-resolution virtual try-on via misalignment-aware normalization. In: Conference on Computer Vision and Pattern Recognition. pp. 14131\u201314140.","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"10.1016\/j.cviu.2026.104661_b6","doi-asserted-by":"crossref","unstructured":"Corona,\u00a0E., Pumarola,\u00a0A., Alenya,\u00a0G., Pons-Moll,\u00a0G., Moreno-Noguer,\u00a0F., 2021. Smplicit: Topology-aware generative model for clothed people. In: Conference on Computer Vision and Pattern Recognition. pp. 11875\u201311885.","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"10.1016\/j.cviu.2026.104661_b7","doi-asserted-by":"crossref","unstructured":"Du,\u00a0C., Yu,\u00a0F., Jiang,\u00a0M., Hua,\u00a0A., Zhao,\u00a0Y., Wei,\u00a0X., Peng,\u00a0T., Hu,\u00a0X., 2022. High fidelity virtual try-on network via semantic adaptation and distributed componentization. In: Computational Visual Media. pp. 649\u2013663.","DOI":"10.1007\/s41095-021-0264-2"},{"key":"10.1016\/j.cviu.2026.104661_b8","doi-asserted-by":"crossref","unstructured":"Ge,\u00a0Y., Song,\u00a0Y., Zhang,\u00a0R., Ge,\u00a0C., Liu,\u00a0W., Luo,\u00a0P., 2021. Parser-free virtual try-on via distilling appearance flows. In: Conference on Computer Vision and Pattern Recognition. pp. 8485\u20138493.","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"10.1016\/j.cviu.2026.104661_b9","doi-asserted-by":"crossref","unstructured":"Grigorev,\u00a0A., Black,\u00a0M.J., Hilliges,\u00a0O., 2023. Hood: Hierarchical graphs for generalized modelling of clothing dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 10822\u201310832.","DOI":"10.1109\/CVPR52729.2023.01627"},{"key":"10.1016\/j.cviu.2026.104661_b10","doi-asserted-by":"crossref","unstructured":"Han,\u00a0X., Hu,\u00a0X., Huang,\u00a0W., Scott,\u00a0M.R., 2019. Clothflow: A flow-based model for clothed person generation. In: Conference on Computer Vision and Pattern Recognition. pp. 10471\u201310480.","DOI":"10.1109\/ICCV.2019.01057"},{"key":"10.1016\/j.cviu.2026.104661_b11","doi-asserted-by":"crossref","unstructured":"Han,\u00a0X., Wu,\u00a0Z., Wu,\u00a0Z., Yu,\u00a0R., Davis,\u00a0L.S., 2018. Viton: An image-based virtual try-on network. In: Conference on Computer Vision and Pattern Recognition. pp. 7543\u20137552.","DOI":"10.1109\/CVPR.2018.00787"},{"key":"10.1016\/j.cviu.2026.104661_b12","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2024.3433526","article-title":"Towards high-fidelity 3D virtual try-on via global collaborative modeling","author":"Hu","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.cviu.2026.104661_b13","doi-asserted-by":"crossref","first-page":"3347","DOI":"10.1007\/s00371-023-02999-4","article-title":"Cloth texture preserving image-based 3D virtual try-on","author":"Hu","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104661_b14","series-title":"Stableviton: Learning semantic correspondence with latent diffusion model for virtual try-on","author":"Kim","year":"2023"},{"key":"10.1016\/j.cviu.2026.104661_b15","doi-asserted-by":"crossref","unstructured":"Lee,\u00a0S., Gu,\u00a0G., Park,\u00a0S., Choi,\u00a0S., Choo,\u00a0J., 2022. High-resolution virtual try-on with misalignment and occlusion-handled conditions. In: European Conference on Computer Vision. pp. 204\u2013219.","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"10.1016\/j.cviu.2026.104661_b16","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Y., Hwangbo,\u00a0S., O\u2019Brien,\u00a0J.F., Pons-Moll,\u00a0G., Yue,\u00a0Y., 2024. Diffavatar: Simulation-ready garment optimization with differentiable simulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR.","DOI":"10.1109\/CVPR52733.2024.00418"},{"key":"10.1016\/j.cviu.2026.104661_b17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2816795.2818013","article-title":"Smpl: A skinned multi-person linear model","volume":"34","author":"Loper","year":"2015","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.cviu.2026.104661_b18","series-title":"Ladi-vton: Latent diffusion textual-inversion enhanced virtual try-on","author":"Morelli","year":"2023"},{"key":"10.1016\/j.cviu.2026.104661_b19","doi-asserted-by":"crossref","unstructured":"Patel,\u00a0C., Liao,\u00a0Z., Pons-Moll,\u00a0G., 2020. Tailornet: Predicting clothing in 3d as a function of human pose, shape and garment style. In: Conference on Computer Vision and Pattern Recognition. pp. 7365\u20137375.","DOI":"10.1109\/CVPR42600.2020.00739"},{"key":"10.1016\/j.cviu.2026.104661_b20","doi-asserted-by":"crossref","unstructured":"Rombach,\u00a0R., Blattmann,\u00a0A., Lorenz,\u00a0D., Esser,\u00a0P., Ommer,\u00a0B., 2022. High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, la, USA, June 18-24, 2022. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.cviu.2026.104661_b21","doi-asserted-by":"crossref","unstructured":"Santesteban,\u00a0I., Thuerey,\u00a0N., Otaduy,\u00a0M.A., Casas,\u00a0D., 2021. Self-supervised collision handling via generative 3d garment models for virtual try-on. In: Conference on Computer Vision and Pattern Recognition. pp. 11763\u201311773.","DOI":"10.1109\/CVPR46437.2021.01159"},{"key":"10.1016\/j.cviu.2026.104661_b22","doi-asserted-by":"crossref","unstructured":"Sarafianos,\u00a0N., Habermann,\u00a0M., Mueller,\u00a0F., Theobalt,\u00a0C., 2025. Garment3dgen: 3d garment stylization and texture generation. In: Proceedings of the IEEE\/CVF International Conference on 3D Vision (3DV).","DOI":"10.1109\/3DV66043.2025.00131"},{"issue":"5","key":"10.1016\/j.cviu.2026.104661_b23","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1007\/s11263-024-02305-2","article-title":"Image-based virtual try-on: A survey","volume":"133","author":"Song","year":"2025","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"issue":"4","key":"10.1016\/j.cviu.2026.104661_b24","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"10.1016\/j.cviu.2026.104661_b25","doi-asserted-by":"crossref","first-page":"4287","DOI":"10.1109\/TCSVT.2024.3521299","article-title":"BetterFit: Accommodate variations in clothing types for virtual try-on","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2026.104661_b26","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0B., Zheng,\u00a0H., Liang,\u00a0X., Chen,\u00a0Y., Lin,\u00a0L., Yang,\u00a0M., 2018. Toward characteristic-preserving image-based virtual try-on network. In: European Conference on Computer Vision. pp. 589\u2013604.","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"10.1016\/j.cviu.2026.104661_b27","doi-asserted-by":"crossref","unstructured":"Xie,\u00a0Z., Huang,\u00a0Z., Dong,\u00a0X., Zhao,\u00a0F., Dong,\u00a0H., Zhang,\u00a0X., Zhu,\u00a0F., Liang,\u00a0X., 2023. Gp-vton: Towards general purpose virtual try-on via collaborative local-flow global-parsing learning. In: Conference on Computer Vision and Pattern Recognition. pp. 23550\u201323559.","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"10.1016\/j.cviu.2026.104661_b28","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0H., Zhang,\u00a0R., Guo,\u00a0X., Liu,\u00a0W., Zuo,\u00a0W., Luo,\u00a0P., 2020. Towards photo-realistic virtual try-on by adaptively generating-preserving image content. In: Conference on Computer Vision and Pattern Recognition. pp. 7850\u20137859.","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"10.1016\/j.cviu.2026.104661_b29","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0Y., Chen,\u00a0L., Zhao,\u00a0H., Liu,\u00a0X., 2024. CAT-DM: Controllable Accelerated Virtual Try-On with Diffusion Model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 8372\u20138382.","DOI":"10.1109\/CVPR52733.2024.00800"},{"key":"10.1016\/j.cviu.2026.104661_b30","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0R., Isola,\u00a0P., Efros,\u00a0A.A., Shechtman,\u00a0E., Wang,\u00a0O., 2018. The unreasonable effectiveness of deep features as a perceptual metric. In: Conference on Computer Vision and Pattern Recognition. pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.cviu.2026.104661_b31","doi-asserted-by":"crossref","unstructured":"Zhu,\u00a0L., Yang,\u00a0D., Zhu,\u00a0T., Reda,\u00a0F., Chan,\u00a0W., Saharia,\u00a0C., Norouzi,\u00a0M., Kemelmacher-Shlizerman,\u00a0I., 2023. Tryondiffusion: A tale of two unets. In: Conference on Computer Vision and Pattern Recognition. pp. 4606\u20134615.","DOI":"10.1109\/CVPR52729.2023.00447"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000287?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000287?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:23:00Z","timestamp":1773987780000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":31,"alternative-id":["S1077314226000287"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104661","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"3D-aware virtual try-on using only 2D inputs","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104661","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104661"}}